核心概念
TwitterメンションとChatGPTは、問題のある記事の未来の取り消しを予測するために有用である。
統計資料
Manual labelling results indicate that there are indeed retracted articles with their Twitter mentions containing recognizable evidence signaling problems before retraction, although they represent only a limited share of all retracted articles with Twitter mention data (approximately 16%).
Using the manual labelling results as the baseline, ChatGPT demonstrates superior performance compared to other methods, implying its potential in assisting human judgment for predicting article retraction.
引述
"Critical Twitter mentions can serve as catalysts in the retraction of problematic articles."
"ChatGPT offers an important advantage over other methods – it can provide reasoning for its predictions."